Problem
Research questions and friction points this paper is trying to address.
long-term memory
personalized AI
dynamical state space
heterogeneous geometry
temporal event stream
Memory Has Geometry: Non-Uniform Geometric Memory for Long-Horizon Personalized AI
🤖 AI Summary
论文提出用非均匀几何记忆空间解决长期个性化AI的记忆表示问题，通过动态状态空间和轨迹重建方法改善记忆访问。
📝 Abstract
Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely static latent space, accessed under one global similarity notion. For data mining, this creates a mismatch: the evidence is a temporal event stream, while the dominant abstraction is a searchable record set. We argue that long-horizon personalization should instead model memory as a user-specific dynamical state space with locally heterogeneous geometry. Geometry here is a computational language, not a literal claim about cognition: it captures stable versus volatile regions, variable-rate drift, heterogeneous neighborhoods, and uncertainty about current user state. Profiles and isolated events remain useful as points, but interaction, feedback, and elapsed time induce trajectories. Memory access then becomes trajectory-conditioned reconstruction of the relevant user state, not only nearest-neighbor lookup.
Innovation
Methods, ideas, or system contributions that make the work stand out.
non-uniform geometric memory
dynamical state space
trajectory-conditioned reconstruction
heterogeneous geometry
🔎 Similar Papers
No similar papers found.
